RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2607.26991v2
• Date: Thu, 30 Jul 2026 04:10:42 GMT
• Title: RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models
• Abstract summary: $RL2$ is an adaptive inference-time steering framework for Vision-Language-Action (VLA) models.<n>We train a lightweight offline RL policy conditioned on expressive latents extracted from the VLA action expert.<n>This compositional steering strategy combines the behavioral priors of large-scale imitation learning with the action diversity induced by offline RL.
• Score: 8.012549967082832
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the impressive visuomotor capabilities enabled by Vision-Language-Action (VLA) models, their performance often degrades on challenging and out-of-domain tasks. Recent test-time steering and scaling methods improve performance without extensive data collection and retraining, but action samples often remain concentrated around similar behaviors and therefore inherit correlated failure modes. Moreover, existing methods apply the same intervention strategy at every timestep, regardless of whether the base policy is already likely to succeed. To address these limitations, we introduce $RL^2$, an adaptive inference-time steering framework that leverages Reinforcement Learning on VLA Latents. First, we train a lightweight offline RL policy conditioned on expressive latents extracted from the VLA action expert and compose its flow velocity with that of the frozen VLA during inference. This compositional steering strategy combines the behavioral priors of large-scale imitation learning with the action diversity induced by offline RL beyond dominant demonstration modes. We further discover that inference-time steering follows fundamentally different scaling laws under success and failure states, revealing that action diversity is most beneficial when the base VLA is likely to fail, but can unnecessarily perturb already-accurate actions when success is likely. Building on this insight, $RL^2$ activates compositional steering only when failure is predicted. Across the SIMPLER and PolaRiS benchmarks, $RL^2$ improves success rates by up to +17.3% in out-of-domain settings, while ablations and scaling studies demonstrate the importance of latent representations and RL training. Finally, real-world experiments demonstrate that these gains transfer beyond simulation, establishing $RL^2$ as a practical and modular steering framework for VLA deployment.

Related papers

• TEMPO: Semantic-Action Decoupled RL Post-Training for Vision-Language-Action Models [8.38821563990503]
  Vision-language-action (VLA) models are commonly adapted to downstream manipulation tasks via supervised fine-tuning (SFT) or online reinforcement learning (RL) post-training.<n>We propose TEMPO, a semantic-action decoupled, two-timescale RL post-training framework for VLA models.<n> Experiments on the CALVIN benchmark and real-world manipulation tasks demonstrate that TEMPO consistently outperforms both pretrained state-of-the-art VLA models and the RL post-training baseline.
  arXiv  Detail & Related papers  (2026-08-07T15:09:51Z)
• ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning [53.17987412112712]
  Reinforcement Learning (RL) has demonstrated significant potential for improving Vision-Language-Action (VLA) models on complex manipulation tasks.<n>In this work, we first investigate the exploration stagnation bottleneck in current VLA-RL frameworks.<n>We introduce RL Exploration Token (ExToken), a simple yet general framework that condition VLA policies on discrete behavioral priors.
  arXiv  Detail & Related papers  (2026-07-14T16:04:41Z)
• dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models [49.497309561043004]
  We propose textbfdVLA-RL, shifting the learning objective from the marginal action probability to the joint probability of the sampled generation path.<n>Our approach achieves a success rate of textbf99.7% on LIBERO.<n>It also establishes strong VLA-based results on RoboTwin 2.0 by delivering a textbf30.6% improvement over the SFT baseline.
  arXiv  Detail & Related papers  (2026-06-22T17:19:03Z)
• Jump-Start Reinforcement Learning with Vision-Language-Action Regularization [1.2599533416395767]
  Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation.<n>Current limitations hinder their direct use in fast and precise manipulation.<n>We propose Vision-Language-Action Jump-Starting (VLAJS) to improve exploration and learning efficiency.
  arXiv  Detail & Related papers  (2026-04-15T11:17:54Z)
• Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures [14.313346858887286]
  Vision-Language-Action (VLA) models for autonomous driving often hit a performance plateau during Reinforcement Learning (RL) optimization.<n>This stagnation arises from exploration capabilities constrained by previous Supervised Fine-Tuning (SFT)<n>We propose Explicit Learning from Failures (ELF-VLA), a framework that augments RL with structured diagnostic feedback.
  arXiv  Detail & Related papers  (2026-03-01T11:41:22Z)
• Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning [88.42566960813438]
  CalibRL is a hybrid-policy RLVR framework that supports controllable exploration with expert guidance.<n>CalibRL increases policy entropy in a guided manner and clarifies the target distribution.<n>Experiments across eight benchmarks, including both in-domain and out-of-domain settings, demonstrate consistent improvements.
  arXiv  Detail & Related papers  (2026-02-22T07:23:36Z)
• Found-RL: foundation model-enhanced reinforcement learning for autonomous driving [15.275134927543611]
  Reinforcement Learning (RL) has emerged as a dominant paradigm for end-to-end autonomous driving (AD)<n>Found-RL is a platform tailored to efficiently enhance RL for AD using foundation models.<n>A core innovation is the asynchronous batch inference framework, which decouples heavy VLM reasoning from the simulation loop.
  arXiv  Detail & Related papers  (2026-02-11T02:56:04Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model [62.889356203346985]
  We propose DUal-STream diffusion (DUST), a world-model augmented VLA framework that handles the modality conflict.<n>DUST achieves up to 6% gains over a standard VLA baseline and implicit world-modeling methods.<n>On real-world tasks with the Franka Research 3, DUST outperforms baselines in success rate by 13%.
  arXiv  Detail & Related papers  (2025-10-31T16:32:12Z)
• SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning [81.7764584515496]
  Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robotic manipulation.<n>These models face two fundamental challenges: scarcity and high cost of large-scale human-operated robotic trajectories.<n>We introduce SimpleVLA-RL, an efficient reinforcement learning framework tailored for VLA models.
  arXiv  Detail & Related papers  (2025-09-11T17:59:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.